besimray commited on
Commit
14971bc
·
verified ·
1 Parent(s): 484b3d9

Upload task output efe665cf-4f36-458e-9e4a-2933f244229e

Browse files
README.md ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: diagonalge/Covenant72B
3
+ library_name: peft
4
+ ---
5
+
6
+ # Model Card for Model ID
7
+
8
+ <!-- Provide a quick summary of what the model is/does. -->
9
+
10
+
11
+
12
+ ## Model Details
13
+
14
+ ### Model Description
15
+
16
+ <!-- Provide a longer summary of what this model is. -->
17
+
18
+
19
+
20
+ - **Developed by:** [More Information Needed]
21
+ - **Funded by [optional]:** [More Information Needed]
22
+ - **Shared by [optional]:** [More Information Needed]
23
+ - **Model type:** [More Information Needed]
24
+ - **Language(s) (NLP):** [More Information Needed]
25
+ - **License:** [More Information Needed]
26
+ - **Finetuned from model [optional]:** [More Information Needed]
27
+
28
+ ### Model Sources [optional]
29
+
30
+ <!-- Provide the basic links for the model. -->
31
+
32
+ - **Repository:** [More Information Needed]
33
+ - **Paper [optional]:** [More Information Needed]
34
+ - **Demo [optional]:** [More Information Needed]
35
+
36
+ ## Uses
37
+
38
+ <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
39
+
40
+ ### Direct Use
41
+
42
+ <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
43
+
44
+ [More Information Needed]
45
+
46
+ ### Downstream Use [optional]
47
+
48
+ <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
49
+
50
+ [More Information Needed]
51
+
52
+ ### Out-of-Scope Use
53
+
54
+ <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
55
+
56
+ [More Information Needed]
57
+
58
+ ## Bias, Risks, and Limitations
59
+
60
+ <!-- This section is meant to convey both technical and sociotechnical limitations. -->
61
+
62
+ [More Information Needed]
63
+
64
+ ### Recommendations
65
+
66
+ <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
67
+
68
+ Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
69
+
70
+ ## How to Get Started with the Model
71
+
72
+ Use the code below to get started with the model.
73
+
74
+ [More Information Needed]
75
+
76
+ ## Training Details
77
+
78
+ ### Training Data
79
+
80
+ <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
81
+
82
+ [More Information Needed]
83
+
84
+ ### Training Procedure
85
+
86
+ <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
87
+
88
+ #### Preprocessing [optional]
89
+
90
+ [More Information Needed]
91
+
92
+
93
+ #### Training Hyperparameters
94
+
95
+ - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
96
+
97
+ #### Speeds, Sizes, Times [optional]
98
+
99
+ <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
100
+
101
+ [More Information Needed]
102
+
103
+ ## Evaluation
104
+
105
+ <!-- This section describes the evaluation protocols and provides the results. -->
106
+
107
+ ### Testing Data, Factors & Metrics
108
+
109
+ #### Testing Data
110
+
111
+ <!-- This should link to a Dataset Card if possible. -->
112
+
113
+ [More Information Needed]
114
+
115
+ #### Factors
116
+
117
+ <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
118
+
119
+ [More Information Needed]
120
+
121
+ #### Metrics
122
+
123
+ <!-- These are the evaluation metrics being used, ideally with a description of why. -->
124
+
125
+ [More Information Needed]
126
+
127
+ ### Results
128
+
129
+ [More Information Needed]
130
+
131
+ #### Summary
132
+
133
+
134
+
135
+ ## Model Examination [optional]
136
+
137
+ <!-- Relevant interpretability work for the model goes here -->
138
+
139
+ [More Information Needed]
140
+
141
+ ## Environmental Impact
142
+
143
+ <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
144
+
145
+ Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
146
+
147
+ - **Hardware Type:** [More Information Needed]
148
+ - **Hours used:** [More Information Needed]
149
+ - **Cloud Provider:** [More Information Needed]
150
+ - **Compute Region:** [More Information Needed]
151
+ - **Carbon Emitted:** [More Information Needed]
152
+
153
+ ## Technical Specifications [optional]
154
+
155
+ ### Model Architecture and Objective
156
+
157
+ [More Information Needed]
158
+
159
+ ### Compute Infrastructure
160
+
161
+ [More Information Needed]
162
+
163
+ #### Hardware
164
+
165
+ [More Information Needed]
166
+
167
+ #### Software
168
+
169
+ [More Information Needed]
170
+
171
+ ## Citation [optional]
172
+
173
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
174
+
175
+ **BibTeX:**
176
+
177
+ [More Information Needed]
178
+
179
+ **APA:**
180
+
181
+ [More Information Needed]
182
+
183
+ ## Glossary [optional]
184
+
185
+ <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
186
+
187
+ [More Information Needed]
188
+
189
+ ## More Information [optional]
190
+
191
+ [More Information Needed]
192
+
193
+ ## Model Card Authors [optional]
194
+
195
+ [More Information Needed]
196
+
197
+ ## Model Card Contact
198
+
199
+ [More Information Needed]
200
+ ### Framework versions
201
+
202
+ - PEFT 0.15.1
adapter_config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "diagonalge/Covenant72B",
5
+ "bias": "none",
6
+ "corda_config": null,
7
+ "eva_config": null,
8
+ "exclude_modules": null,
9
+ "fan_in_fan_out": false,
10
+ "inference_mode": true,
11
+ "init_lora_weights": true,
12
+ "layer_replication": null,
13
+ "layers_pattern": null,
14
+ "layers_to_transform": null,
15
+ "loftq_config": {},
16
+ "lora_alpha": 512,
17
+ "lora_bias": false,
18
+ "lora_dropout": 0.1,
19
+ "megatron_config": null,
20
+ "megatron_core": "megatron.core",
21
+ "modules_to_save": null,
22
+ "peft_type": "LORA",
23
+ "r": 128,
24
+ "rank_pattern": {},
25
+ "revision": null,
26
+ "target_modules": [
27
+ "o_proj",
28
+ "gate_proj",
29
+ "k_proj",
30
+ "up_proj",
31
+ "q_proj",
32
+ "v_proj",
33
+ "down_proj"
34
+ ],
35
+ "task_type": "CAUSAL_LM",
36
+ "trainable_token_indices": null,
37
+ "use_dora": false,
38
+ "use_rslora": false
39
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b0e556b0bc384fe0b780b4b635c36c8e72ac82491d26941ed9b6b3d742bda23
3
+ size 3313655720
loss.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ 1251,1.5202196836471558
trainer_state.json ADDED
@@ -0,0 +1,1824 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 2.936619718309859,
6
+ "eval_steps": 500,
7
+ "global_step": 1251,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.011737089201877934,
14
+ "grad_norm": 1.6926082666941107,
15
+ "learning_rate": 9.237540571428572e-06,
16
+ "loss": 4.1191,
17
+ "step": 5
18
+ },
19
+ {
20
+ "epoch": 0.023474178403755867,
21
+ "grad_norm": 1.0523580952405567,
22
+ "learning_rate": 2.0784466285714287e-05,
23
+ "loss": 3.9165,
24
+ "step": 10
25
+ },
26
+ {
27
+ "epoch": 0.035211267605633804,
28
+ "grad_norm": 0.9348982322725803,
29
+ "learning_rate": 3.2331392000000005e-05,
30
+ "loss": 3.0751,
31
+ "step": 15
32
+ },
33
+ {
34
+ "epoch": 0.046948356807511735,
35
+ "grad_norm": 0.963142977085111,
36
+ "learning_rate": 4.3878317714285716e-05,
37
+ "loss": 2.3471,
38
+ "step": 20
39
+ },
40
+ {
41
+ "epoch": 0.05868544600938967,
42
+ "grad_norm": 0.41999800522000985,
43
+ "learning_rate": 5.542524342857144e-05,
44
+ "loss": 1.9358,
45
+ "step": 25
46
+ },
47
+ {
48
+ "epoch": 0.07042253521126761,
49
+ "grad_norm": 0.44353131458171546,
50
+ "learning_rate": 6.697216914285716e-05,
51
+ "loss": 1.8648,
52
+ "step": 30
53
+ },
54
+ {
55
+ "epoch": 0.08215962441314555,
56
+ "grad_norm": 1.3157403937206136,
57
+ "learning_rate": 7.851909485714286e-05,
58
+ "loss": 1.874,
59
+ "step": 35
60
+ },
61
+ {
62
+ "epoch": 0.09389671361502347,
63
+ "grad_norm": 0.30804693051898663,
64
+ "learning_rate": 8.082693104266452e-05,
65
+ "loss": 1.8383,
66
+ "step": 40
67
+ },
68
+ {
69
+ "epoch": 0.1056338028169014,
70
+ "grad_norm": 0.27001251328292725,
71
+ "learning_rate": 8.082063867481342e-05,
72
+ "loss": 1.4036,
73
+ "step": 45
74
+ },
75
+ {
76
+ "epoch": 0.11737089201877934,
77
+ "grad_norm": 0.3485335678060715,
78
+ "learning_rate": 8.080950709070086e-05,
79
+ "loss": 1.6265,
80
+ "step": 50
81
+ },
82
+ {
83
+ "epoch": 0.12910798122065728,
84
+ "grad_norm": 0.25009903952840973,
85
+ "learning_rate": 8.079353806798678e-05,
86
+ "loss": 1.5537,
87
+ "step": 55
88
+ },
89
+ {
90
+ "epoch": 0.14084507042253522,
91
+ "grad_norm": 0.283472870261176,
92
+ "learning_rate": 8.07727341568466e-05,
93
+ "loss": 1.5242,
94
+ "step": 60
95
+ },
96
+ {
97
+ "epoch": 0.15258215962441316,
98
+ "grad_norm": 0.2603618862170815,
99
+ "learning_rate": 8.074709867956397e-05,
100
+ "loss": 1.52,
101
+ "step": 65
102
+ },
103
+ {
104
+ "epoch": 0.1643192488262911,
105
+ "grad_norm": 0.26748765076963404,
106
+ "learning_rate": 8.071663573000018e-05,
107
+ "loss": 1.4147,
108
+ "step": 70
109
+ },
110
+ {
111
+ "epoch": 0.176056338028169,
112
+ "grad_norm": 0.27233224635502085,
113
+ "learning_rate": 8.068135017294043e-05,
114
+ "loss": 1.4277,
115
+ "step": 75
116
+ },
117
+ {
118
+ "epoch": 0.18779342723004694,
119
+ "grad_norm": 0.27807424769416844,
120
+ "learning_rate": 8.064124764331693e-05,
121
+ "loss": 1.5202,
122
+ "step": 80
123
+ },
124
+ {
125
+ "epoch": 0.19953051643192488,
126
+ "grad_norm": 0.237501219160123,
127
+ "learning_rate": 8.059633454530899e-05,
128
+ "loss": 1.5265,
129
+ "step": 85
130
+ },
131
+ {
132
+ "epoch": 0.2112676056338028,
133
+ "grad_norm": 0.26393741964527623,
134
+ "learning_rate": 8.054661805132042e-05,
135
+ "loss": 1.4661,
136
+ "step": 90
137
+ },
138
+ {
139
+ "epoch": 0.22300469483568075,
140
+ "grad_norm": 0.307134230448153,
141
+ "learning_rate": 8.049210610083398e-05,
142
+ "loss": 1.5281,
143
+ "step": 95
144
+ },
145
+ {
146
+ "epoch": 0.2347417840375587,
147
+ "grad_norm": 0.30034381561230195,
148
+ "learning_rate": 8.043280739914361e-05,
149
+ "loss": 1.4272,
150
+ "step": 100
151
+ },
152
+ {
153
+ "epoch": 0.24647887323943662,
154
+ "grad_norm": 0.25199182793601094,
155
+ "learning_rate": 8.036873141596414e-05,
156
+ "loss": 1.385,
157
+ "step": 105
158
+ },
159
+ {
160
+ "epoch": 0.25821596244131456,
161
+ "grad_norm": 0.25027218831718984,
162
+ "learning_rate": 8.029988838391911e-05,
163
+ "loss": 1.4313,
164
+ "step": 110
165
+ },
166
+ {
167
+ "epoch": 0.2699530516431925,
168
+ "grad_norm": 1.0436457556233485,
169
+ "learning_rate": 8.02262892969066e-05,
170
+ "loss": 1.4076,
171
+ "step": 115
172
+ },
173
+ {
174
+ "epoch": 0.28169014084507044,
175
+ "grad_norm": 0.25287945938151374,
176
+ "learning_rate": 8.014794590834359e-05,
177
+ "loss": 1.4006,
178
+ "step": 120
179
+ },
180
+ {
181
+ "epoch": 0.2934272300469484,
182
+ "grad_norm": 0.3426017772114307,
183
+ "learning_rate": 8.0064870729289e-05,
184
+ "loss": 1.3478,
185
+ "step": 125
186
+ },
187
+ {
188
+ "epoch": 0.3051643192488263,
189
+ "grad_norm": 0.24548095078180857,
190
+ "learning_rate": 7.997707702644572e-05,
191
+ "loss": 1.4508,
192
+ "step": 130
193
+ },
194
+ {
195
+ "epoch": 0.31690140845070425,
196
+ "grad_norm": 0.3257280042891666,
197
+ "learning_rate": 7.988457882004198e-05,
198
+ "loss": 1.3507,
199
+ "step": 135
200
+ },
201
+ {
202
+ "epoch": 0.3286384976525822,
203
+ "grad_norm": 0.2648447775178709,
204
+ "learning_rate": 7.978739088159242e-05,
205
+ "loss": 1.3959,
206
+ "step": 140
207
+ },
208
+ {
209
+ "epoch": 0.3403755868544601,
210
+ "grad_norm": 0.3253574365810539,
211
+ "learning_rate": 7.968552873153908e-05,
212
+ "loss": 1.5608,
213
+ "step": 145
214
+ },
215
+ {
216
+ "epoch": 0.352112676056338,
217
+ "grad_norm": 0.2683217685759068,
218
+ "learning_rate": 7.957900863677296e-05,
219
+ "loss": 1.3742,
220
+ "step": 150
221
+ },
222
+ {
223
+ "epoch": 0.36384976525821594,
224
+ "grad_norm": 0.27823469209609253,
225
+ "learning_rate": 7.94678476080362e-05,
226
+ "loss": 1.4693,
227
+ "step": 155
228
+ },
229
+ {
230
+ "epoch": 0.3755868544600939,
231
+ "grad_norm": 0.31396185033997276,
232
+ "learning_rate": 7.935206339720553e-05,
233
+ "loss": 1.4293,
234
+ "step": 160
235
+ },
236
+ {
237
+ "epoch": 0.3873239436619718,
238
+ "grad_norm": 0.23711923917761538,
239
+ "learning_rate": 7.923167449445751e-05,
240
+ "loss": 1.3614,
241
+ "step": 165
242
+ },
243
+ {
244
+ "epoch": 0.39906103286384975,
245
+ "grad_norm": 0.23098090222216835,
246
+ "learning_rate": 7.910670012531556e-05,
247
+ "loss": 1.4348,
248
+ "step": 170
249
+ },
250
+ {
251
+ "epoch": 0.4107981220657277,
252
+ "grad_norm": 0.24726241172120542,
253
+ "learning_rate": 7.897716024757991e-05,
254
+ "loss": 1.3991,
255
+ "step": 175
256
+ },
257
+ {
258
+ "epoch": 0.4225352112676056,
259
+ "grad_norm": 0.2529598203448259,
260
+ "learning_rate": 7.884307554814028e-05,
261
+ "loss": 1.3889,
262
+ "step": 180
263
+ },
264
+ {
265
+ "epoch": 0.43427230046948356,
266
+ "grad_norm": 0.2626838974550443,
267
+ "learning_rate": 7.870446743967242e-05,
268
+ "loss": 1.3164,
269
+ "step": 185
270
+ },
271
+ {
272
+ "epoch": 0.4460093896713615,
273
+ "grad_norm": 0.22340503189330538,
274
+ "learning_rate": 7.856135805721846e-05,
275
+ "loss": 1.3403,
276
+ "step": 190
277
+ },
278
+ {
279
+ "epoch": 0.45774647887323944,
280
+ "grad_norm": 0.2643635528374707,
281
+ "learning_rate": 7.841377025465227e-05,
282
+ "loss": 1.3128,
283
+ "step": 195
284
+ },
285
+ {
286
+ "epoch": 0.4694835680751174,
287
+ "grad_norm": 0.23702382238947953,
288
+ "learning_rate": 7.826172760102954e-05,
289
+ "loss": 1.3577,
290
+ "step": 200
291
+ },
292
+ {
293
+ "epoch": 0.4812206572769953,
294
+ "grad_norm": 0.3089050115416261,
295
+ "learning_rate": 7.810525437682417e-05,
296
+ "loss": 1.3627,
297
+ "step": 205
298
+ },
299
+ {
300
+ "epoch": 0.49295774647887325,
301
+ "grad_norm": 0.2459426412330782,
302
+ "learning_rate": 7.794437557005058e-05,
303
+ "loss": 1.361,
304
+ "step": 210
305
+ },
306
+ {
307
+ "epoch": 0.5046948356807511,
308
+ "grad_norm": 0.2474645086201422,
309
+ "learning_rate": 7.777911687227339e-05,
310
+ "loss": 1.35,
311
+ "step": 215
312
+ },
313
+ {
314
+ "epoch": 0.5164319248826291,
315
+ "grad_norm": 0.2776269910713455,
316
+ "learning_rate": 7.760950467450457e-05,
317
+ "loss": 1.3038,
318
+ "step": 220
319
+ },
320
+ {
321
+ "epoch": 0.528169014084507,
322
+ "grad_norm": 0.23093548062400274,
323
+ "learning_rate": 7.743556606298887e-05,
324
+ "loss": 1.2999,
325
+ "step": 225
326
+ },
327
+ {
328
+ "epoch": 0.539906103286385,
329
+ "grad_norm": 0.21029555812416517,
330
+ "learning_rate": 7.725732881487837e-05,
331
+ "loss": 1.3563,
332
+ "step": 230
333
+ },
334
+ {
335
+ "epoch": 0.5516431924882629,
336
+ "grad_norm": 0.2380837640644916,
337
+ "learning_rate": 7.707482139379649e-05,
338
+ "loss": 1.4117,
339
+ "step": 235
340
+ },
341
+ {
342
+ "epoch": 0.5633802816901409,
343
+ "grad_norm": 0.2501691778817746,
344
+ "learning_rate": 7.688807294529259e-05,
345
+ "loss": 1.3747,
346
+ "step": 240
347
+ },
348
+ {
349
+ "epoch": 0.5751173708920188,
350
+ "grad_norm": 0.2531422248522496,
351
+ "learning_rate": 7.669711329218748e-05,
352
+ "loss": 1.3142,
353
+ "step": 245
354
+ },
355
+ {
356
+ "epoch": 0.5868544600938967,
357
+ "grad_norm": 0.3071530417375628,
358
+ "learning_rate": 7.6501972929811e-05,
359
+ "loss": 1.3518,
360
+ "step": 250
361
+ },
362
+ {
363
+ "epoch": 0.5985915492957746,
364
+ "grad_norm": 0.2462933779162881,
365
+ "learning_rate": 7.630268302113184e-05,
366
+ "loss": 1.3381,
367
+ "step": 255
368
+ },
369
+ {
370
+ "epoch": 0.6103286384976526,
371
+ "grad_norm": 0.231440592355059,
372
+ "learning_rate": 7.609927539178122e-05,
373
+ "loss": 1.2967,
374
+ "step": 260
375
+ },
376
+ {
377
+ "epoch": 0.6220657276995305,
378
+ "grad_norm": 0.26883215485587464,
379
+ "learning_rate": 7.589178252497026e-05,
380
+ "loss": 1.4204,
381
+ "step": 265
382
+ },
383
+ {
384
+ "epoch": 0.6338028169014085,
385
+ "grad_norm": 1.5499941567046591,
386
+ "learning_rate": 7.568023755630275e-05,
387
+ "loss": 1.2625,
388
+ "step": 270
389
+ },
390
+ {
391
+ "epoch": 0.6455399061032864,
392
+ "grad_norm": 0.23176606216751602,
393
+ "learning_rate": 7.546467426848345e-05,
394
+ "loss": 1.3575,
395
+ "step": 275
396
+ },
397
+ {
398
+ "epoch": 0.6572769953051644,
399
+ "grad_norm": 0.29787341630319236,
400
+ "learning_rate": 7.524512708592318e-05,
401
+ "loss": 1.3631,
402
+ "step": 280
403
+ },
404
+ {
405
+ "epoch": 0.6690140845070423,
406
+ "grad_norm": 0.2414950159288888,
407
+ "learning_rate": 7.502163106924143e-05,
408
+ "loss": 1.3421,
409
+ "step": 285
410
+ },
411
+ {
412
+ "epoch": 0.6807511737089202,
413
+ "grad_norm": 0.2609054694114428,
414
+ "learning_rate": 7.479422190966731e-05,
415
+ "loss": 1.2775,
416
+ "step": 290
417
+ },
418
+ {
419
+ "epoch": 0.6924882629107981,
420
+ "grad_norm": 0.24342075714638725,
421
+ "learning_rate": 7.456293592333991e-05,
422
+ "loss": 1.2399,
423
+ "step": 295
424
+ },
425
+ {
426
+ "epoch": 0.704225352112676,
427
+ "grad_norm": 0.2451126010921149,
428
+ "learning_rate": 7.432781004550864e-05,
429
+ "loss": 1.1849,
430
+ "step": 300
431
+ },
432
+ {
433
+ "epoch": 0.715962441314554,
434
+ "grad_norm": 0.38381425009051096,
435
+ "learning_rate": 7.408888182463507e-05,
436
+ "loss": 1.2887,
437
+ "step": 305
438
+ },
439
+ {
440
+ "epoch": 0.7276995305164319,
441
+ "grad_norm": 0.23592915827608676,
442
+ "learning_rate": 7.38461894163964e-05,
443
+ "loss": 1.3505,
444
+ "step": 310
445
+ },
446
+ {
447
+ "epoch": 0.7394366197183099,
448
+ "grad_norm": 0.2698206782214951,
449
+ "learning_rate": 7.35997715775923e-05,
450
+ "loss": 1.3215,
451
+ "step": 315
452
+ },
453
+ {
454
+ "epoch": 0.7511737089201878,
455
+ "grad_norm": 0.2453301887513675,
456
+ "learning_rate": 7.334966765995569e-05,
457
+ "loss": 1.2296,
458
+ "step": 320
459
+ },
460
+ {
461
+ "epoch": 0.7629107981220657,
462
+ "grad_norm": 0.21952063652943296,
463
+ "learning_rate": 7.309591760386829e-05,
464
+ "loss": 1.3247,
465
+ "step": 325
466
+ },
467
+ {
468
+ "epoch": 0.7746478873239436,
469
+ "grad_norm": 0.28692324866840146,
470
+ "learning_rate": 7.28385619319825e-05,
471
+ "loss": 1.2973,
472
+ "step": 330
473
+ },
474
+ {
475
+ "epoch": 0.7863849765258216,
476
+ "grad_norm": 0.24556875494678596,
477
+ "learning_rate": 7.257764174275004e-05,
478
+ "loss": 1.1292,
479
+ "step": 335
480
+ },
481
+ {
482
+ "epoch": 0.7981220657276995,
483
+ "grad_norm": 0.21102775812196028,
484
+ "learning_rate": 7.231319870385874e-05,
485
+ "loss": 1.1703,
486
+ "step": 340
487
+ },
488
+ {
489
+ "epoch": 0.8098591549295775,
490
+ "grad_norm": 0.22043483877271167,
491
+ "learning_rate": 7.204527504557848e-05,
492
+ "loss": 1.1836,
493
+ "step": 345
494
+ },
495
+ {
496
+ "epoch": 0.8215962441314554,
497
+ "grad_norm": 0.23022946831058466,
498
+ "learning_rate": 7.177391355401707e-05,
499
+ "loss": 1.3726,
500
+ "step": 350
501
+ },
502
+ {
503
+ "epoch": 0.8333333333333334,
504
+ "grad_norm": 0.2246896571930163,
505
+ "learning_rate": 7.149915756428768e-05,
506
+ "loss": 1.3799,
507
+ "step": 355
508
+ },
509
+ {
510
+ "epoch": 0.8450704225352113,
511
+ "grad_norm": 0.2523792044709292,
512
+ "learning_rate": 7.122105095358836e-05,
513
+ "loss": 1.3122,
514
+ "step": 360
515
+ },
516
+ {
517
+ "epoch": 0.8568075117370892,
518
+ "grad_norm": 0.23559138914799244,
519
+ "learning_rate": 7.0939638134195e-05,
520
+ "loss": 1.2995,
521
+ "step": 365
522
+ },
523
+ {
524
+ "epoch": 0.8685446009389671,
525
+ "grad_norm": 0.2597889434863669,
526
+ "learning_rate": 7.065496404636905e-05,
527
+ "loss": 1.369,
528
+ "step": 370
529
+ },
530
+ {
531
+ "epoch": 0.8802816901408451,
532
+ "grad_norm": 0.24829748827668763,
533
+ "learning_rate": 7.036707415118069e-05,
534
+ "loss": 1.2793,
535
+ "step": 375
536
+ },
537
+ {
538
+ "epoch": 0.892018779342723,
539
+ "grad_norm": 0.6851956453951893,
540
+ "learning_rate": 7.007601442324886e-05,
541
+ "loss": 1.3262,
542
+ "step": 380
543
+ },
544
+ {
545
+ "epoch": 0.903755868544601,
546
+ "grad_norm": 0.24078658149556825,
547
+ "learning_rate": 6.978183134339949e-05,
548
+ "loss": 1.3209,
549
+ "step": 385
550
+ },
551
+ {
552
+ "epoch": 0.9154929577464789,
553
+ "grad_norm": 0.24167241236562123,
554
+ "learning_rate": 6.948457189124259e-05,
555
+ "loss": 1.3779,
556
+ "step": 390
557
+ },
558
+ {
559
+ "epoch": 0.9272300469483568,
560
+ "grad_norm": 0.24575130336431836,
561
+ "learning_rate": 6.918428353766991e-05,
562
+ "loss": 1.3325,
563
+ "step": 395
564
+ },
565
+ {
566
+ "epoch": 0.9389671361502347,
567
+ "grad_norm": 0.2326601273504395,
568
+ "learning_rate": 6.888101423727413e-05,
569
+ "loss": 1.2331,
570
+ "step": 400
571
+ },
572
+ {
573
+ "epoch": 0.9507042253521126,
574
+ "grad_norm": 0.22591521946130988,
575
+ "learning_rate": 6.857481242069052e-05,
576
+ "loss": 1.2541,
577
+ "step": 405
578
+ },
579
+ {
580
+ "epoch": 0.9624413145539906,
581
+ "grad_norm": 0.2308511630846233,
582
+ "learning_rate": 6.82657269868631e-05,
583
+ "loss": 1.2298,
584
+ "step": 410
585
+ },
586
+ {
587
+ "epoch": 0.9741784037558685,
588
+ "grad_norm": 0.25182225001294944,
589
+ "learning_rate": 6.795380729523547e-05,
590
+ "loss": 1.301,
591
+ "step": 415
592
+ },
593
+ {
594
+ "epoch": 0.9859154929577465,
595
+ "grad_norm": 0.2605089795549262,
596
+ "learning_rate": 6.76391031578685e-05,
597
+ "loss": 1.3731,
598
+ "step": 420
599
+ },
600
+ {
601
+ "epoch": 0.9976525821596244,
602
+ "grad_norm": 0.22892211041701857,
603
+ "learning_rate": 6.732166483148549e-05,
604
+ "loss": 1.1978,
605
+ "step": 425
606
+ },
607
+ {
608
+ "epoch": 0.9976525821596244,
609
+ "eval_loss": 1.6044145822525024,
610
+ "eval_runtime": 50.0629,
611
+ "eval_samples_per_second": 1.458,
612
+ "eval_steps_per_second": 0.2,
613
+ "step": 425
614
+ },
615
+ {
616
+ "epoch": 1.0093896713615023,
617
+ "grad_norm": 0.24910638304822852,
618
+ "learning_rate": 6.70015430094465e-05,
619
+ "loss": 1.123,
620
+ "step": 430
621
+ },
622
+ {
623
+ "epoch": 1.0211267605633803,
624
+ "grad_norm": 0.33357404745827773,
625
+ "learning_rate": 6.667878881365277e-05,
626
+ "loss": 1.1185,
627
+ "step": 435
628
+ },
629
+ {
630
+ "epoch": 1.0328638497652582,
631
+ "grad_norm": 0.29008454147641954,
632
+ "learning_rate": 6.635345378638292e-05,
633
+ "loss": 1.1284,
634
+ "step": 440
635
+ },
636
+ {
637
+ "epoch": 1.0446009389671362,
638
+ "grad_norm": 0.2670483776495452,
639
+ "learning_rate": 6.602558988206174e-05,
640
+ "loss": 1.2331,
641
+ "step": 445
642
+ },
643
+ {
644
+ "epoch": 1.056338028169014,
645
+ "grad_norm": 0.2430183857087479,
646
+ "learning_rate": 6.56952494589635e-05,
647
+ "loss": 1.0354,
648
+ "step": 450
649
+ },
650
+ {
651
+ "epoch": 1.068075117370892,
652
+ "grad_norm": 0.25159392522233937,
653
+ "learning_rate": 6.536248527085044e-05,
654
+ "loss": 1.095,
655
+ "step": 455
656
+ },
657
+ {
658
+ "epoch": 1.07981220657277,
659
+ "grad_norm": 0.25129604646154363,
660
+ "learning_rate": 6.502735045854836e-05,
661
+ "loss": 1.1631,
662
+ "step": 460
663
+ },
664
+ {
665
+ "epoch": 1.091549295774648,
666
+ "grad_norm": 0.2375727576097195,
667
+ "learning_rate": 6.468989854146017e-05,
668
+ "loss": 1.056,
669
+ "step": 465
670
+ },
671
+ {
672
+ "epoch": 1.1032863849765258,
673
+ "grad_norm": 0.25705262164871134,
674
+ "learning_rate": 6.435018340901922e-05,
675
+ "loss": 1.1019,
676
+ "step": 470
677
+ },
678
+ {
679
+ "epoch": 1.1150234741784038,
680
+ "grad_norm": 0.2632363761365353,
681
+ "learning_rate": 6.400825931208336e-05,
682
+ "loss": 1.0925,
683
+ "step": 475
684
+ },
685
+ {
686
+ "epoch": 1.1267605633802817,
687
+ "grad_norm": 0.25529732934150606,
688
+ "learning_rate": 6.366418085427133e-05,
689
+ "loss": 1.0742,
690
+ "step": 480
691
+ },
692
+ {
693
+ "epoch": 1.1384976525821595,
694
+ "grad_norm": 0.24911618052576018,
695
+ "learning_rate": 6.331800298324286e-05,
696
+ "loss": 1.1257,
697
+ "step": 485
698
+ },
699
+ {
700
+ "epoch": 1.1502347417840375,
701
+ "grad_norm": 0.2713693928567898,
702
+ "learning_rate": 6.29697809819238e-05,
703
+ "loss": 1.1852,
704
+ "step": 490
705
+ },
706
+ {
707
+ "epoch": 1.1619718309859155,
708
+ "grad_norm": 0.25598293691462287,
709
+ "learning_rate": 6.26195704596776e-05,
710
+ "loss": 1.147,
711
+ "step": 495
712
+ },
713
+ {
714
+ "epoch": 1.1737089201877935,
715
+ "grad_norm": 0.2506209145241536,
716
+ "learning_rate": 6.2267427343425e-05,
717
+ "loss": 1.0602,
718
+ "step": 500
719
+ },
720
+ {
721
+ "epoch": 1.1737089201877935,
722
+ "eval_loss": 1.5600786209106445,
723
+ "eval_runtime": 49.8763,
724
+ "eval_samples_per_second": 1.464,
725
+ "eval_steps_per_second": 0.2,
726
+ "step": 500
727
+ },
728
+ {
729
+ "epoch": 1.1854460093896715,
730
+ "grad_norm": 0.24306048622973317,
731
+ "learning_rate": 6.19134078687125e-05,
732
+ "loss": 1.0243,
733
+ "step": 505
734
+ },
735
+ {
736
+ "epoch": 1.1971830985915493,
737
+ "grad_norm": 0.26647005420227804,
738
+ "learning_rate": 6.155756857073197e-05,
739
+ "loss": 1.1676,
740
+ "step": 510
741
+ },
742
+ {
743
+ "epoch": 1.2089201877934272,
744
+ "grad_norm": 0.28346081980702725,
745
+ "learning_rate": 6.119996627529222e-05,
746
+ "loss": 1.1091,
747
+ "step": 515
748
+ },
749
+ {
750
+ "epoch": 1.2206572769953052,
751
+ "grad_norm": 0.2523758910052274,
752
+ "learning_rate": 6.084065808974423e-05,
753
+ "loss": 1.1431,
754
+ "step": 520
755
+ },
756
+ {
757
+ "epoch": 1.232394366197183,
758
+ "grad_norm": 0.24326518180467072,
759
+ "learning_rate": 6.047970139386133e-05,
760
+ "loss": 1.0999,
761
+ "step": 525
762
+ },
763
+ {
764
+ "epoch": 1.244131455399061,
765
+ "grad_norm": 0.2517876789791905,
766
+ "learning_rate": 6.011715383067593e-05,
767
+ "loss": 1.1285,
768
+ "step": 530
769
+ },
770
+ {
771
+ "epoch": 1.255868544600939,
772
+ "grad_norm": 0.25670486692069977,
773
+ "learning_rate": 5.975307329727426e-05,
774
+ "loss": 1.0623,
775
+ "step": 535
776
+ },
777
+ {
778
+ "epoch": 1.267605633802817,
779
+ "grad_norm": 0.2831263117979734,
780
+ "learning_rate": 5.938751793555044e-05,
781
+ "loss": 1.1384,
782
+ "step": 540
783
+ },
784
+ {
785
+ "epoch": 1.2793427230046948,
786
+ "grad_norm": 0.2514294700936478,
787
+ "learning_rate": 5.902054612292151e-05,
788
+ "loss": 1.1115,
789
+ "step": 545
790
+ },
791
+ {
792
+ "epoch": 1.2910798122065728,
793
+ "grad_norm": 0.2830207243631822,
794
+ "learning_rate": 5.865221646300485e-05,
795
+ "loss": 1.1742,
796
+ "step": 550
797
+ },
798
+ {
799
+ "epoch": 1.3028169014084507,
800
+ "grad_norm": 0.27398863839678606,
801
+ "learning_rate": 5.828258777625944e-05,
802
+ "loss": 1.1052,
803
+ "step": 555
804
+ },
805
+ {
806
+ "epoch": 1.3145539906103285,
807
+ "grad_norm": 0.25895033553118535,
808
+ "learning_rate": 5.791171909059259e-05,
809
+ "loss": 1.2186,
810
+ "step": 560
811
+ },
812
+ {
813
+ "epoch": 1.3262910798122065,
814
+ "grad_norm": 0.258186822849988,
815
+ "learning_rate": 5.7539669631933385e-05,
816
+ "loss": 1.1201,
817
+ "step": 565
818
+ },
819
+ {
820
+ "epoch": 1.3380281690140845,
821
+ "grad_norm": 0.25129851535157616,
822
+ "learning_rate": 5.71664988147746e-05,
823
+ "loss": 1.1031,
824
+ "step": 570
825
+ },
826
+ {
827
+ "epoch": 1.3497652582159625,
828
+ "grad_norm": 0.25982425225157424,
829
+ "learning_rate": 5.6792266232684574e-05,
830
+ "loss": 1.0259,
831
+ "step": 575
832
+ },
833
+ {
834
+ "epoch": 1.3615023474178405,
835
+ "grad_norm": 0.26067740399731576,
836
+ "learning_rate": 5.6417031648790324e-05,
837
+ "loss": 1.2319,
838
+ "step": 580
839
+ },
840
+ {
841
+ "epoch": 1.3732394366197183,
842
+ "grad_norm": 0.28203855843767645,
843
+ "learning_rate": 5.6040854986233706e-05,
844
+ "loss": 1.1523,
845
+ "step": 585
846
+ },
847
+ {
848
+ "epoch": 1.3849765258215962,
849
+ "grad_norm": 0.2616034024922836,
850
+ "learning_rate": 5.5663796318601946e-05,
851
+ "loss": 1.0862,
852
+ "step": 590
853
+ },
854
+ {
855
+ "epoch": 1.3967136150234742,
856
+ "grad_norm": 0.2557988750857973,
857
+ "learning_rate": 5.528591586033421e-05,
858
+ "loss": 1.1261,
859
+ "step": 595
860
+ },
861
+ {
862
+ "epoch": 1.408450704225352,
863
+ "grad_norm": 0.2583387594345229,
864
+ "learning_rate": 5.490727395710563e-05,
865
+ "loss": 1.1638,
866
+ "step": 600
867
+ },
868
+ {
869
+ "epoch": 1.42018779342723,
870
+ "grad_norm": 0.2824039637269599,
871
+ "learning_rate": 5.452793107619043e-05,
872
+ "loss": 1.1064,
873
+ "step": 605
874
+ },
875
+ {
876
+ "epoch": 1.431924882629108,
877
+ "grad_norm": 0.30378896985216747,
878
+ "learning_rate": 5.4147947796805546e-05,
879
+ "loss": 1.1587,
880
+ "step": 610
881
+ },
882
+ {
883
+ "epoch": 1.443661971830986,
884
+ "grad_norm": 0.26055491232191014,
885
+ "learning_rate": 5.376738480043643e-05,
886
+ "loss": 1.1737,
887
+ "step": 615
888
+ },
889
+ {
890
+ "epoch": 1.455399061032864,
891
+ "grad_norm": 0.28775987096455746,
892
+ "learning_rate": 5.338630286114656e-05,
893
+ "loss": 1.0302,
894
+ "step": 620
895
+ },
896
+ {
897
+ "epoch": 1.4671361502347418,
898
+ "grad_norm": 0.27434540717537476,
899
+ "learning_rate": 5.300476283587205e-05,
900
+ "loss": 1.096,
901
+ "step": 625
902
+ },
903
+ {
904
+ "epoch": 1.4788732394366197,
905
+ "grad_norm": 0.2687633406815332,
906
+ "learning_rate": 5.262282565470313e-05,
907
+ "loss": 1.1784,
908
+ "step": 630
909
+ },
910
+ {
911
+ "epoch": 1.4906103286384975,
912
+ "grad_norm": 0.30497461697387473,
913
+ "learning_rate": 5.224055231115389e-05,
914
+ "loss": 1.0557,
915
+ "step": 635
916
+ },
917
+ {
918
+ "epoch": 1.5023474178403755,
919
+ "grad_norm": 0.2401646558924421,
920
+ "learning_rate": 5.185800385242196e-05,
921
+ "loss": 1.2208,
922
+ "step": 640
923
+ },
924
+ {
925
+ "epoch": 1.5140845070422535,
926
+ "grad_norm": 0.28302252582641413,
927
+ "learning_rate": 5.147524136963947e-05,
928
+ "loss": 1.1629,
929
+ "step": 645
930
+ },
931
+ {
932
+ "epoch": 1.5258215962441315,
933
+ "grad_norm": 0.2733981765032047,
934
+ "learning_rate": 5.1092325988117195e-05,
935
+ "loss": 1.1179,
936
+ "step": 650
937
+ },
938
+ {
939
+ "epoch": 1.5375586854460095,
940
+ "grad_norm": 0.3543210495906027,
941
+ "learning_rate": 5.0709318857583076e-05,
942
+ "loss": 1.1171,
943
+ "step": 655
944
+ },
945
+ {
946
+ "epoch": 1.5492957746478875,
947
+ "grad_norm": 0.2678160500016965,
948
+ "learning_rate": 5.032628114241694e-05,
949
+ "loss": 1.1378,
950
+ "step": 660
951
+ },
952
+ {
953
+ "epoch": 1.5610328638497653,
954
+ "grad_norm": 0.2841104290261492,
955
+ "learning_rate": 4.994327401188283e-05,
956
+ "loss": 1.1317,
957
+ "step": 665
958
+ },
959
+ {
960
+ "epoch": 1.5727699530516432,
961
+ "grad_norm": 0.23756976664123616,
962
+ "learning_rate": 4.956035863036055e-05,
963
+ "loss": 1.1054,
964
+ "step": 670
965
+ },
966
+ {
967
+ "epoch": 1.584507042253521,
968
+ "grad_norm": 0.299042726296967,
969
+ "learning_rate": 4.9177596147578067e-05,
970
+ "loss": 1.14,
971
+ "step": 675
972
+ },
973
+ {
974
+ "epoch": 1.596244131455399,
975
+ "grad_norm": 0.24219892354659045,
976
+ "learning_rate": 4.879504768884612e-05,
977
+ "loss": 1.2392,
978
+ "step": 680
979
+ },
980
+ {
981
+ "epoch": 1.607981220657277,
982
+ "grad_norm": 0.2659120257163632,
983
+ "learning_rate": 4.841277434529689e-05,
984
+ "loss": 1.076,
985
+ "step": 685
986
+ },
987
+ {
988
+ "epoch": 1.619718309859155,
989
+ "grad_norm": 0.2535490633175144,
990
+ "learning_rate": 4.803083716412797e-05,
991
+ "loss": 1.1433,
992
+ "step": 690
993
+ },
994
+ {
995
+ "epoch": 1.631455399061033,
996
+ "grad_norm": 0.2601946247918616,
997
+ "learning_rate": 4.764929713885346e-05,
998
+ "loss": 1.1151,
999
+ "step": 695
1000
+ },
1001
+ {
1002
+ "epoch": 1.6431924882629108,
1003
+ "grad_norm": 0.2510924947348151,
1004
+ "learning_rate": 4.726821519956359e-05,
1005
+ "loss": 1.1195,
1006
+ "step": 700
1007
+ },
1008
+ {
1009
+ "epoch": 1.6549295774647887,
1010
+ "grad_norm": 0.2717853110326184,
1011
+ "learning_rate": 4.688765220319449e-05,
1012
+ "loss": 1.0717,
1013
+ "step": 705
1014
+ },
1015
+ {
1016
+ "epoch": 1.6666666666666665,
1017
+ "grad_norm": 0.29413144596709895,
1018
+ "learning_rate": 4.65076689238096e-05,
1019
+ "loss": 1.1293,
1020
+ "step": 710
1021
+ },
1022
+ {
1023
+ "epoch": 1.6784037558685445,
1024
+ "grad_norm": 0.260973856516902,
1025
+ "learning_rate": 4.61283260428944e-05,
1026
+ "loss": 1.0877,
1027
+ "step": 715
1028
+ },
1029
+ {
1030
+ "epoch": 1.6901408450704225,
1031
+ "grad_norm": 0.24688922048601705,
1032
+ "learning_rate": 4.574968413966582e-05,
1033
+ "loss": 1.074,
1034
+ "step": 720
1035
+ },
1036
+ {
1037
+ "epoch": 1.7018779342723005,
1038
+ "grad_norm": 0.29518134961553794,
1039
+ "learning_rate": 4.537180368139808e-05,
1040
+ "loss": 1.2313,
1041
+ "step": 725
1042
+ },
1043
+ {
1044
+ "epoch": 1.7136150234741785,
1045
+ "grad_norm": 0.2789615734091057,
1046
+ "learning_rate": 4.499474501376632e-05,
1047
+ "loss": 1.0704,
1048
+ "step": 730
1049
+ },
1050
+ {
1051
+ "epoch": 1.7253521126760565,
1052
+ "grad_norm": 0.2658926149309144,
1053
+ "learning_rate": 4.461856835120969e-05,
1054
+ "loss": 1.0596,
1055
+ "step": 735
1056
+ },
1057
+ {
1058
+ "epoch": 1.7370892018779343,
1059
+ "grad_norm": 0.2572838262933699,
1060
+ "learning_rate": 4.424333376731544e-05,
1061
+ "loss": 1.1131,
1062
+ "step": 740
1063
+ },
1064
+ {
1065
+ "epoch": 1.7488262910798122,
1066
+ "grad_norm": 0.2771724916201255,
1067
+ "learning_rate": 4.386910118522542e-05,
1068
+ "loss": 1.1371,
1069
+ "step": 745
1070
+ },
1071
+ {
1072
+ "epoch": 1.76056338028169,
1073
+ "grad_norm": 0.27676486532377537,
1074
+ "learning_rate": 4.349593036806664e-05,
1075
+ "loss": 1.0967,
1076
+ "step": 750
1077
+ },
1078
+ {
1079
+ "epoch": 1.772300469483568,
1080
+ "grad_norm": 0.26672550277720775,
1081
+ "learning_rate": 4.3123880909407424e-05,
1082
+ "loss": 1.0533,
1083
+ "step": 755
1084
+ },
1085
+ {
1086
+ "epoch": 1.784037558685446,
1087
+ "grad_norm": 0.23662667298158832,
1088
+ "learning_rate": 4.275301222374057e-05,
1089
+ "loss": 1.0783,
1090
+ "step": 760
1091
+ },
1092
+ {
1093
+ "epoch": 1.795774647887324,
1094
+ "grad_norm": 0.29383896298290885,
1095
+ "learning_rate": 4.238338353699518e-05,
1096
+ "loss": 1.17,
1097
+ "step": 765
1098
+ },
1099
+ {
1100
+ "epoch": 1.807511737089202,
1101
+ "grad_norm": 0.28154071670327757,
1102
+ "learning_rate": 4.201505387707851e-05,
1103
+ "loss": 1.1453,
1104
+ "step": 770
1105
+ },
1106
+ {
1107
+ "epoch": 1.8192488262910798,
1108
+ "grad_norm": 0.25700361275731554,
1109
+ "learning_rate": 4.1648082064449574e-05,
1110
+ "loss": 1.082,
1111
+ "step": 775
1112
+ },
1113
+ {
1114
+ "epoch": 1.8309859154929577,
1115
+ "grad_norm": 0.2826122217432797,
1116
+ "learning_rate": 4.128252670272575e-05,
1117
+ "loss": 1.0474,
1118
+ "step": 780
1119
+ },
1120
+ {
1121
+ "epoch": 1.8427230046948355,
1122
+ "grad_norm": 0.2620920138050905,
1123
+ "learning_rate": 4.091844616932409e-05,
1124
+ "loss": 1.1321,
1125
+ "step": 785
1126
+ },
1127
+ {
1128
+ "epoch": 1.8544600938967135,
1129
+ "grad_norm": 0.29154525087785954,
1130
+ "learning_rate": 4.055589860613869e-05,
1131
+ "loss": 1.1328,
1132
+ "step": 790
1133
+ },
1134
+ {
1135
+ "epoch": 1.8661971830985915,
1136
+ "grad_norm": 0.2619470877476919,
1137
+ "learning_rate": 4.01949419102558e-05,
1138
+ "loss": 1.0941,
1139
+ "step": 795
1140
+ },
1141
+ {
1142
+ "epoch": 1.8779342723004695,
1143
+ "grad_norm": 0.24822033480152877,
1144
+ "learning_rate": 3.983563372470781e-05,
1145
+ "loss": 0.9679,
1146
+ "step": 800
1147
+ },
1148
+ {
1149
+ "epoch": 1.8896713615023475,
1150
+ "grad_norm": 0.28224783656544505,
1151
+ "learning_rate": 3.9478031429268066e-05,
1152
+ "loss": 1.144,
1153
+ "step": 805
1154
+ },
1155
+ {
1156
+ "epoch": 1.9014084507042255,
1157
+ "grad_norm": 0.30516183723950785,
1158
+ "learning_rate": 3.912219213128753e-05,
1159
+ "loss": 1.1058,
1160
+ "step": 810
1161
+ },
1162
+ {
1163
+ "epoch": 1.9131455399061033,
1164
+ "grad_norm": 0.30562651002624985,
1165
+ "learning_rate": 3.876817265657502e-05,
1166
+ "loss": 1.1647,
1167
+ "step": 815
1168
+ },
1169
+ {
1170
+ "epoch": 1.9248826291079812,
1171
+ "grad_norm": 0.2768262798277747,
1172
+ "learning_rate": 3.8416029540322404e-05,
1173
+ "loss": 1.1273,
1174
+ "step": 820
1175
+ },
1176
+ {
1177
+ "epoch": 1.936619718309859,
1178
+ "grad_norm": 0.2842898850002602,
1179
+ "learning_rate": 3.806581901807623e-05,
1180
+ "loss": 1.1984,
1181
+ "step": 825
1182
+ },
1183
+ {
1184
+ "epoch": 1.948356807511737,
1185
+ "grad_norm": 0.31329090267496584,
1186
+ "learning_rate": 3.771759701675715e-05,
1187
+ "loss": 1.1333,
1188
+ "step": 830
1189
+ },
1190
+ {
1191
+ "epoch": 1.960093896713615,
1192
+ "grad_norm": 0.3381345989557091,
1193
+ "learning_rate": 3.7371419145728696e-05,
1194
+ "loss": 1.0973,
1195
+ "step": 835
1196
+ },
1197
+ {
1198
+ "epoch": 1.971830985915493,
1199
+ "grad_norm": 0.2970165089739574,
1200
+ "learning_rate": 3.702734068791666e-05,
1201
+ "loss": 1.1552,
1202
+ "step": 840
1203
+ },
1204
+ {
1205
+ "epoch": 1.983568075117371,
1206
+ "grad_norm": 0.26229774431947867,
1207
+ "learning_rate": 3.6685416590980806e-05,
1208
+ "loss": 1.0432,
1209
+ "step": 845
1210
+ },
1211
+ {
1212
+ "epoch": 1.995305164319249,
1213
+ "grad_norm": 0.3020477793486203,
1214
+ "learning_rate": 3.634570145853985e-05,
1215
+ "loss": 1.1401,
1216
+ "step": 850
1217
+ },
1218
+ {
1219
+ "epoch": 1.995305164319249,
1220
+ "eval_loss": 1.5306791067123413,
1221
+ "eval_runtime": 51.0959,
1222
+ "eval_samples_per_second": 1.429,
1223
+ "eval_steps_per_second": 0.196,
1224
+ "step": 850
1225
+ },
1226
+ {
1227
+ "epoch": 2.007042253521127,
1228
+ "grad_norm": 0.24436801124041757,
1229
+ "learning_rate": 3.600824954145166e-05,
1230
+ "loss": 0.9757,
1231
+ "step": 855
1232
+ },
1233
+ {
1234
+ "epoch": 2.0187793427230045,
1235
+ "grad_norm": 0.3332860055486253,
1236
+ "learning_rate": 3.567311472914957e-05,
1237
+ "loss": 0.9992,
1238
+ "step": 860
1239
+ },
1240
+ {
1241
+ "epoch": 2.0305164319248825,
1242
+ "grad_norm": 0.2915663428907029,
1243
+ "learning_rate": 3.5340350541036516e-05,
1244
+ "loss": 0.9287,
1245
+ "step": 865
1246
+ },
1247
+ {
1248
+ "epoch": 2.0422535211267605,
1249
+ "grad_norm": 0.31218559752172226,
1250
+ "learning_rate": 3.501001011793828e-05,
1251
+ "loss": 0.8744,
1252
+ "step": 870
1253
+ },
1254
+ {
1255
+ "epoch": 2.0539906103286385,
1256
+ "grad_norm": 0.3014812239987984,
1257
+ "learning_rate": 3.46821462136171e-05,
1258
+ "loss": 0.7871,
1259
+ "step": 875
1260
+ },
1261
+ {
1262
+ "epoch": 2.0657276995305165,
1263
+ "grad_norm": 0.2919198189363655,
1264
+ "learning_rate": 3.4356811186347255e-05,
1265
+ "loss": 0.8375,
1266
+ "step": 880
1267
+ },
1268
+ {
1269
+ "epoch": 2.0774647887323945,
1270
+ "grad_norm": 0.30297421951074827,
1271
+ "learning_rate": 3.4034056990553525e-05,
1272
+ "loss": 0.9539,
1273
+ "step": 885
1274
+ },
1275
+ {
1276
+ "epoch": 2.0892018779342725,
1277
+ "grad_norm": 0.3004785475460889,
1278
+ "learning_rate": 3.3713935168514526e-05,
1279
+ "loss": 0.8916,
1280
+ "step": 890
1281
+ },
1282
+ {
1283
+ "epoch": 2.10093896713615,
1284
+ "grad_norm": 0.3063305424781025,
1285
+ "learning_rate": 3.339649684213153e-05,
1286
+ "loss": 0.8923,
1287
+ "step": 895
1288
+ },
1289
+ {
1290
+ "epoch": 2.112676056338028,
1291
+ "grad_norm": 0.3087837541879336,
1292
+ "learning_rate": 3.308179270476455e-05,
1293
+ "loss": 0.9808,
1294
+ "step": 900
1295
+ },
1296
+ {
1297
+ "epoch": 2.124413145539906,
1298
+ "grad_norm": 0.3069084480862884,
1299
+ "learning_rate": 3.276987301313693e-05,
1300
+ "loss": 0.9499,
1301
+ "step": 905
1302
+ },
1303
+ {
1304
+ "epoch": 2.136150234741784,
1305
+ "grad_norm": 0.31772408652498,
1306
+ "learning_rate": 3.246078757930949e-05,
1307
+ "loss": 0.9302,
1308
+ "step": 910
1309
+ },
1310
+ {
1311
+ "epoch": 2.147887323943662,
1312
+ "grad_norm": 0.32823640884020344,
1313
+ "learning_rate": 3.21545857627259e-05,
1314
+ "loss": 0.8977,
1315
+ "step": 915
1316
+ },
1317
+ {
1318
+ "epoch": 2.15962441314554,
1319
+ "grad_norm": 0.2986661375144512,
1320
+ "learning_rate": 3.1851316462330086e-05,
1321
+ "loss": 0.9632,
1322
+ "step": 920
1323
+ },
1324
+ {
1325
+ "epoch": 2.171361502347418,
1326
+ "grad_norm": 0.3044796130319778,
1327
+ "learning_rate": 3.155102810875744e-05,
1328
+ "loss": 0.9244,
1329
+ "step": 925
1330
+ },
1331
+ {
1332
+ "epoch": 2.183098591549296,
1333
+ "grad_norm": 0.29391562913639346,
1334
+ "learning_rate": 3.125376865660053e-05,
1335
+ "loss": 0.9065,
1336
+ "step": 930
1337
+ },
1338
+ {
1339
+ "epoch": 2.1948356807511735,
1340
+ "grad_norm": 0.33464998182357986,
1341
+ "learning_rate": 3.095958557675115e-05,
1342
+ "loss": 1.0646,
1343
+ "step": 935
1344
+ },
1345
+ {
1346
+ "epoch": 2.2065727699530515,
1347
+ "grad_norm": 0.3097450215029285,
1348
+ "learning_rate": 3.0668525848819334e-05,
1349
+ "loss": 0.909,
1350
+ "step": 940
1351
+ },
1352
+ {
1353
+ "epoch": 2.2183098591549295,
1354
+ "grad_norm": 0.31619368356156724,
1355
+ "learning_rate": 3.0380635953630954e-05,
1356
+ "loss": 0.942,
1357
+ "step": 945
1358
+ },
1359
+ {
1360
+ "epoch": 2.2300469483568075,
1361
+ "grad_norm": 0.5488021620297451,
1362
+ "learning_rate": 3.009596186580501e-05,
1363
+ "loss": 0.9037,
1364
+ "step": 950
1365
+ },
1366
+ {
1367
+ "epoch": 2.2417840375586855,
1368
+ "grad_norm": 0.3007995564402941,
1369
+ "learning_rate": 2.981454904641166e-05,
1370
+ "loss": 0.841,
1371
+ "step": 955
1372
+ },
1373
+ {
1374
+ "epoch": 2.2535211267605635,
1375
+ "grad_norm": 1.0143926976429458,
1376
+ "learning_rate": 2.953644243571233e-05,
1377
+ "loss": 0.8931,
1378
+ "step": 960
1379
+ },
1380
+ {
1381
+ "epoch": 2.2652582159624415,
1382
+ "grad_norm": 0.32847505150062767,
1383
+ "learning_rate": 2.926168644598294e-05,
1384
+ "loss": 0.8939,
1385
+ "step": 965
1386
+ },
1387
+ {
1388
+ "epoch": 2.276995305164319,
1389
+ "grad_norm": 0.29868200806169454,
1390
+ "learning_rate": 2.899032495442154e-05,
1391
+ "loss": 0.877,
1392
+ "step": 970
1393
+ },
1394
+ {
1395
+ "epoch": 2.288732394366197,
1396
+ "grad_norm": 0.3247314434075676,
1397
+ "learning_rate": 2.8722401296141272e-05,
1398
+ "loss": 0.9554,
1399
+ "step": 975
1400
+ },
1401
+ {
1402
+ "epoch": 2.300469483568075,
1403
+ "grad_norm": 0.2963994274935962,
1404
+ "learning_rate": 2.845795825724998e-05,
1405
+ "loss": 0.8366,
1406
+ "step": 980
1407
+ },
1408
+ {
1409
+ "epoch": 2.312206572769953,
1410
+ "grad_norm": 0.3018384484277062,
1411
+ "learning_rate": 2.819703806801753e-05,
1412
+ "loss": 0.9772,
1413
+ "step": 985
1414
+ },
1415
+ {
1416
+ "epoch": 2.323943661971831,
1417
+ "grad_norm": 0.3138452072040482,
1418
+ "learning_rate": 2.7939682396131733e-05,
1419
+ "loss": 0.8705,
1420
+ "step": 990
1421
+ },
1422
+ {
1423
+ "epoch": 2.335680751173709,
1424
+ "grad_norm": 0.33495040627076267,
1425
+ "learning_rate": 2.7685932340044337e-05,
1426
+ "loss": 0.9398,
1427
+ "step": 995
1428
+ },
1429
+ {
1430
+ "epoch": 2.347417840375587,
1431
+ "grad_norm": 0.3426786719758913,
1432
+ "learning_rate": 2.743582842240771e-05,
1433
+ "loss": 0.9528,
1434
+ "step": 1000
1435
+ },
1436
+ {
1437
+ "epoch": 2.347417840375587,
1438
+ "eval_loss": 1.5564570426940918,
1439
+ "eval_runtime": 49.772,
1440
+ "eval_samples_per_second": 1.467,
1441
+ "eval_steps_per_second": 0.201,
1442
+ "step": 1000
1443
+ },
1444
+ {
1445
+ "epoch": 2.359154929577465,
1446
+ "grad_norm": 0.32715481854051526,
1447
+ "learning_rate": 2.7189410583603632e-05,
1448
+ "loss": 0.9294,
1449
+ "step": 1005
1450
+ },
1451
+ {
1452
+ "epoch": 2.370892018779343,
1453
+ "grad_norm": 0.31904903206727697,
1454
+ "learning_rate": 2.6946718175364948e-05,
1455
+ "loss": 0.9377,
1456
+ "step": 1010
1457
+ },
1458
+ {
1459
+ "epoch": 2.3826291079812205,
1460
+ "grad_norm": 0.3246876100683689,
1461
+ "learning_rate": 2.6707789954491374e-05,
1462
+ "loss": 0.9389,
1463
+ "step": 1015
1464
+ },
1465
+ {
1466
+ "epoch": 2.3943661971830985,
1467
+ "grad_norm": 0.33657822136933685,
1468
+ "learning_rate": 2.647266407666012e-05,
1469
+ "loss": 0.8748,
1470
+ "step": 1020
1471
+ },
1472
+ {
1473
+ "epoch": 2.4061032863849765,
1474
+ "grad_norm": 0.33075950831011175,
1475
+ "learning_rate": 2.62413780903327e-05,
1476
+ "loss": 0.9191,
1477
+ "step": 1025
1478
+ },
1479
+ {
1480
+ "epoch": 2.4178403755868545,
1481
+ "grad_norm": 0.3091789648897354,
1482
+ "learning_rate": 2.6013968930758587e-05,
1483
+ "loss": 0.8542,
1484
+ "step": 1030
1485
+ },
1486
+ {
1487
+ "epoch": 2.4295774647887325,
1488
+ "grad_norm": 0.3017557854181004,
1489
+ "learning_rate": 2.579047291407683e-05,
1490
+ "loss": 0.9691,
1491
+ "step": 1035
1492
+ },
1493
+ {
1494
+ "epoch": 2.4413145539906105,
1495
+ "grad_norm": 0.3315662930965317,
1496
+ "learning_rate": 2.557092573151657e-05,
1497
+ "loss": 0.9335,
1498
+ "step": 1040
1499
+ },
1500
+ {
1501
+ "epoch": 2.453051643192488,
1502
+ "grad_norm": 0.28405648990544513,
1503
+ "learning_rate": 2.5355362443697268e-05,
1504
+ "loss": 0.8608,
1505
+ "step": 1045
1506
+ },
1507
+ {
1508
+ "epoch": 2.464788732394366,
1509
+ "grad_norm": 0.3272098198440713,
1510
+ "learning_rate": 2.5143817475029763e-05,
1511
+ "loss": 0.945,
1512
+ "step": 1050
1513
+ },
1514
+ {
1515
+ "epoch": 2.476525821596244,
1516
+ "grad_norm": 15.473459249206623,
1517
+ "learning_rate": 2.4936324608218807e-05,
1518
+ "loss": 0.862,
1519
+ "step": 1055
1520
+ },
1521
+ {
1522
+ "epoch": 2.488262910798122,
1523
+ "grad_norm": 0.3214221685785962,
1524
+ "learning_rate": 2.4732916978868173e-05,
1525
+ "loss": 0.8372,
1526
+ "step": 1060
1527
+ },
1528
+ {
1529
+ "epoch": 2.5,
1530
+ "grad_norm": 0.30527745666926165,
1531
+ "learning_rate": 2.453362707018903e-05,
1532
+ "loss": 0.9094,
1533
+ "step": 1065
1534
+ },
1535
+ {
1536
+ "epoch": 2.511737089201878,
1537
+ "grad_norm": 0.337431832474658,
1538
+ "learning_rate": 2.4338486707812528e-05,
1539
+ "loss": 0.8946,
1540
+ "step": 1070
1541
+ },
1542
+ {
1543
+ "epoch": 2.523474178403756,
1544
+ "grad_norm": 0.3322583740691652,
1545
+ "learning_rate": 2.414752705470744e-05,
1546
+ "loss": 0.949,
1547
+ "step": 1075
1548
+ },
1549
+ {
1550
+ "epoch": 2.535211267605634,
1551
+ "grad_norm": 0.3183558468618594,
1552
+ "learning_rate": 2.396077860620353e-05,
1553
+ "loss": 0.8969,
1554
+ "step": 1080
1555
+ },
1556
+ {
1557
+ "epoch": 2.546948356807512,
1558
+ "grad_norm": 0.3155273530496357,
1559
+ "learning_rate": 2.377827118512165e-05,
1560
+ "loss": 0.9395,
1561
+ "step": 1085
1562
+ },
1563
+ {
1564
+ "epoch": 2.5586854460093895,
1565
+ "grad_norm": 2.4170816896900025,
1566
+ "learning_rate": 2.3600033937011134e-05,
1567
+ "loss": 0.8337,
1568
+ "step": 1090
1569
+ },
1570
+ {
1571
+ "epoch": 2.5704225352112675,
1572
+ "grad_norm": 0.31607546736128544,
1573
+ "learning_rate": 2.342609532549545e-05,
1574
+ "loss": 0.856,
1575
+ "step": 1095
1576
+ },
1577
+ {
1578
+ "epoch": 2.5821596244131455,
1579
+ "grad_norm": 0.33297406422032433,
1580
+ "learning_rate": 2.3256483127726626e-05,
1581
+ "loss": 0.8664,
1582
+ "step": 1100
1583
+ },
1584
+ {
1585
+ "epoch": 2.5938967136150235,
1586
+ "grad_norm": 0.3237147629308357,
1587
+ "learning_rate": 2.309122442994944e-05,
1588
+ "loss": 0.8719,
1589
+ "step": 1105
1590
+ },
1591
+ {
1592
+ "epoch": 2.6056338028169015,
1593
+ "grad_norm": 0.3234191361238395,
1594
+ "learning_rate": 2.2930345623175854e-05,
1595
+ "loss": 0.9487,
1596
+ "step": 1110
1597
+ },
1598
+ {
1599
+ "epoch": 2.6173708920187795,
1600
+ "grad_norm": 0.3323839887038311,
1601
+ "learning_rate": 2.277387239897046e-05,
1602
+ "loss": 0.9493,
1603
+ "step": 1115
1604
+ },
1605
+ {
1606
+ "epoch": 2.629107981220657,
1607
+ "grad_norm": 0.32228378417361714,
1608
+ "learning_rate": 2.262182974534775e-05,
1609
+ "loss": 0.8866,
1610
+ "step": 1120
1611
+ },
1612
+ {
1613
+ "epoch": 2.640845070422535,
1614
+ "grad_norm": 0.3079696625324963,
1615
+ "learning_rate": 2.247424194278155e-05,
1616
+ "loss": 0.8054,
1617
+ "step": 1125
1618
+ },
1619
+ {
1620
+ "epoch": 2.652582159624413,
1621
+ "grad_norm": 0.3097789983846638,
1622
+ "learning_rate": 2.2331132560327617e-05,
1623
+ "loss": 0.9464,
1624
+ "step": 1130
1625
+ },
1626
+ {
1627
+ "epoch": 2.664319248826291,
1628
+ "grad_norm": 0.29487479541027356,
1629
+ "learning_rate": 2.2192524451859738e-05,
1630
+ "loss": 0.9063,
1631
+ "step": 1135
1632
+ },
1633
+ {
1634
+ "epoch": 2.676056338028169,
1635
+ "grad_norm": 0.33006135046655793,
1636
+ "learning_rate": 2.205843975242011e-05,
1637
+ "loss": 0.8962,
1638
+ "step": 1140
1639
+ },
1640
+ {
1641
+ "epoch": 2.687793427230047,
1642
+ "grad_norm": 0.3529330284339669,
1643
+ "learning_rate": 2.1928899874684446e-05,
1644
+ "loss": 0.9958,
1645
+ "step": 1145
1646
+ },
1647
+ {
1648
+ "epoch": 2.699530516431925,
1649
+ "grad_norm": 0.36979938140870244,
1650
+ "learning_rate": 2.1803925505542516e-05,
1651
+ "loss": 0.9466,
1652
+ "step": 1150
1653
+ },
1654
+ {
1655
+ "epoch": 2.711267605633803,
1656
+ "grad_norm": 0.30449528011099597,
1657
+ "learning_rate": 2.168353660279449e-05,
1658
+ "loss": 0.8422,
1659
+ "step": 1155
1660
+ },
1661
+ {
1662
+ "epoch": 2.723004694835681,
1663
+ "grad_norm": 0.32449892199883407,
1664
+ "learning_rate": 2.156775239196383e-05,
1665
+ "loss": 0.9596,
1666
+ "step": 1160
1667
+ },
1668
+ {
1669
+ "epoch": 2.7347417840375585,
1670
+ "grad_norm": 0.3082491729387956,
1671
+ "learning_rate": 2.145659136322706e-05,
1672
+ "loss": 0.8846,
1673
+ "step": 1165
1674
+ },
1675
+ {
1676
+ "epoch": 2.7464788732394365,
1677
+ "grad_norm": 0.3542469454397538,
1678
+ "learning_rate": 2.1350071268460934e-05,
1679
+ "loss": 0.9162,
1680
+ "step": 1170
1681
+ },
1682
+ {
1683
+ "epoch": 2.7582159624413145,
1684
+ "grad_norm": 0.35364030378555145,
1685
+ "learning_rate": 2.12482091184076e-05,
1686
+ "loss": 0.9548,
1687
+ "step": 1175
1688
+ },
1689
+ {
1690
+ "epoch": 2.7699530516431925,
1691
+ "grad_norm": 0.534630830850989,
1692
+ "learning_rate": 2.115102117995803e-05,
1693
+ "loss": 0.9527,
1694
+ "step": 1180
1695
+ },
1696
+ {
1697
+ "epoch": 2.7816901408450705,
1698
+ "grad_norm": 0.3638700943894012,
1699
+ "learning_rate": 2.1058522973554294e-05,
1700
+ "loss": 0.8624,
1701
+ "step": 1185
1702
+ },
1703
+ {
1704
+ "epoch": 2.7934272300469485,
1705
+ "grad_norm": 0.33210932308224567,
1706
+ "learning_rate": 2.0970729270711017e-05,
1707
+ "loss": 0.8602,
1708
+ "step": 1190
1709
+ },
1710
+ {
1711
+ "epoch": 2.805164319248826,
1712
+ "grad_norm": 0.3271576610317457,
1713
+ "learning_rate": 2.0887654091656426e-05,
1714
+ "loss": 0.8537,
1715
+ "step": 1195
1716
+ },
1717
+ {
1718
+ "epoch": 2.816901408450704,
1719
+ "grad_norm": 0.3445497480228464,
1720
+ "learning_rate": 2.0809310703093418e-05,
1721
+ "loss": 0.805,
1722
+ "step": 1200
1723
+ },
1724
+ {
1725
+ "epoch": 2.828638497652582,
1726
+ "grad_norm": 0.32705975575158863,
1727
+ "learning_rate": 2.073571161608091e-05,
1728
+ "loss": 0.955,
1729
+ "step": 1205
1730
+ },
1731
+ {
1732
+ "epoch": 2.84037558685446,
1733
+ "grad_norm": 0.34134786803880485,
1734
+ "learning_rate": 2.066686858403588e-05,
1735
+ "loss": 0.907,
1736
+ "step": 1210
1737
+ },
1738
+ {
1739
+ "epoch": 2.852112676056338,
1740
+ "grad_norm": 0.31253357487176564,
1741
+ "learning_rate": 2.0602792600856414e-05,
1742
+ "loss": 0.9051,
1743
+ "step": 1215
1744
+ },
1745
+ {
1746
+ "epoch": 2.863849765258216,
1747
+ "grad_norm": 0.3325144520719963,
1748
+ "learning_rate": 2.0543493899166034e-05,
1749
+ "loss": 0.9146,
1750
+ "step": 1220
1751
+ },
1752
+ {
1753
+ "epoch": 2.875586854460094,
1754
+ "grad_norm": 0.3293615881469167,
1755
+ "learning_rate": 2.04889819486796e-05,
1756
+ "loss": 0.8378,
1757
+ "step": 1225
1758
+ },
1759
+ {
1760
+ "epoch": 2.887323943661972,
1761
+ "grad_norm": 0.33386869136878455,
1762
+ "learning_rate": 2.0439265454691023e-05,
1763
+ "loss": 0.9188,
1764
+ "step": 1230
1765
+ },
1766
+ {
1767
+ "epoch": 2.89906103286385,
1768
+ "grad_norm": 0.32510298043861213,
1769
+ "learning_rate": 2.0394352356683095e-05,
1770
+ "loss": 0.9314,
1771
+ "step": 1235
1772
+ },
1773
+ {
1774
+ "epoch": 2.910798122065728,
1775
+ "grad_norm": 0.3244639716190284,
1776
+ "learning_rate": 2.0354249827059588e-05,
1777
+ "loss": 0.8556,
1778
+ "step": 1240
1779
+ },
1780
+ {
1781
+ "epoch": 2.9225352112676055,
1782
+ "grad_norm": 0.3442224853352613,
1783
+ "learning_rate": 2.0318964269999837e-05,
1784
+ "loss": 0.8086,
1785
+ "step": 1245
1786
+ },
1787
+ {
1788
+ "epoch": 2.9342723004694835,
1789
+ "grad_norm": 0.3402662522070222,
1790
+ "learning_rate": 2.0288501320436047e-05,
1791
+ "loss": 0.8865,
1792
+ "step": 1250
1793
+ },
1794
+ {
1795
+ "epoch": 2.936619718309859,
1796
+ "eval_loss": 1.5202196836471558,
1797
+ "eval_runtime": 49.8279,
1798
+ "eval_samples_per_second": 1.465,
1799
+ "eval_steps_per_second": 0.201,
1800
+ "step": 1251
1801
+ }
1802
+ ],
1803
+ "logging_steps": 5,
1804
+ "max_steps": 1278,
1805
+ "num_input_tokens_seen": 0,
1806
+ "num_train_epochs": 3,
1807
+ "save_steps": 500,
1808
+ "stateful_callbacks": {
1809
+ "TrainerControl": {
1810
+ "args": {
1811
+ "should_epoch_stop": false,
1812
+ "should_evaluate": false,
1813
+ "should_log": false,
1814
+ "should_save": true,
1815
+ "should_training_stop": false
1816
+ },
1817
+ "attributes": {}
1818
+ }
1819
+ },
1820
+ "total_flos": 1297580487081984.0,
1821
+ "train_batch_size": 8,
1822
+ "trial_name": null,
1823
+ "trial_params": null
1824
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5066bbeeb25eb080a35ab58de809bd30050b716bf0b552d366620369d9522bc5
3
+ size 7480